.png){kind=icon}
Resembles the one-group pretest-posttest design except multiple observations are made before and after the treatment.
Pretests and posttests are administered to experimental conditions but random assignment is not possible.
May occur when measurement of the dependent variable varies over time or experimental conditions.
Loss of subjects varies across experimental conditions.
The effect of X on Y depends on Z.
May be confounded with the independent variable when a single group is studied over an extended period of time.
A matter of how well an experiment controls for the effects of extraneous variables.
An experiment in which two or more variables are manipulated.
A threat to internal validity when a single group is measured at two or more points in time.
Randomization rules out this threat to internal validity.
A potential threat to validity when subjects are selected on the basis of their extreme scores on the dependent variable.
This design eliminates the possibility of testing-X interaction.